DOCSLIB.ORG

Reliability Analysis of Artificial Intelligence Systems Using

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Reliability Analysis of Artificial Intelligence Systems Using Reliability Analysis of Artificial Intelligence Systems Using Recurrent Events Data from Autonomous Vehicles Yili Hong1, Jie Min1, Caleb B. King2, and William Q. Meeker3 1Department of Statistics, Virginia Tech, Blacksburg, VA 24061 2JMP Division, SAS, Cary, NC 27513 3Department of Statistics, Iowa State University, Ames, IA 50011 Abstract Artificial intelligence (AI) systems have become increasingly common and the trend will continue. Examples of AI systems include autonomous vehicles (AV), computer vi- sion, natural language processing, and AI medical experts. To allow for safe and effective deployment of AI systems, the reliability of such systems needs to be assessed. Tradition- ally, reliability assessment is based on reliability test data and the subsequent statistical modeling and analysis. The availability of reliability data for AI systems, however, is limited because such data are typically sensitive and proprietary. The California Depart- ment of Motor Vehicles (DMV) oversees and regulates an AV testing program, in which many AV manufacturers are conducting AV road tests. Manufacturers participating in the program are required to report recurrent disengagement events to California DMV. This information is being made available to the public. In this paper, we use recurrent disengagement events as a representation of the reliability of the AI system in AV, and propose a statistical framework for modeling and analyzing the recurrent events data arXiv:2102.01740v1 [cs.AI] 2 Feb 2021 from AV driving tests. We use traditional parametric models in software reliability and propose a new nonparametric model based on monotonic splines to describe the event process. We develop inference procedures for selecting the best models, quantifying un- certainty, and testing heterogeneity in the event process. We then analyze the recurrent events data from four AV manufacturers, and make inferences on the reliability of the AI systems in AV. We also describe how the proposed analysis can be applied to assess the reliability of other AI systems. Key Words: Disengagement Events; Fractional Random Weight Bootstrap; Gom- pertz Model; Monotonic Splines; Software Reliability; Self-driving Cars. 1 1 Introduction 1.1 The Problem With the rapid development of new technology, artificial intelligence (AI) systems are emerg- ing in many areas. Typical applications of AI systems include autonomous vehicles (AV), computer vision, speech recognition, and AI medical experts. The reliability and safety of AI systems need to be assessed before massive deployment in the field. For example, the reliability of AV needs to be demonstrated so that people can use them with confidence. Traditionally, reliability assessment of products and systems is based on reliability test data collected from the laboratory and the field. Reliability information is then extracted from statistical modeling and analysis of the data. Commonly used data types for reliability analysis are time-to-event data, degradation data, and recurrent events data. Reliability data collected by manufacturers are highly sensitive and are usually not publicly available. In the area of AV, however, the California Department of Motor Vehicles (DMV) has launched an AV driving program. More details of the study are given in Section 2. Many AV manufacturers are participating in the program and are conducting AV road test in California. Manufacturers are required to report disengagement events and mileage information to the California DMV. The reported events are available for public access. Because of the availability of these recurrent events data, we focus on the reliability analysis of the AI systems in AV units in this paper. A disengagement event happens when the AI system and/or the backup driver determines that the driver needs to take over the driving. The recurrence rates of disengagement events can be used as a proxy for the reliability of the AI system in AV. A lower occurrence rate (event rate) of disengagement events would indicate a more reliable AI system in the AV. In the reliability literature, parametric forms have been used to describe the event rate through a nonhomogeneous Poisson process (NHPP) model. In practice, some specific questions arise in the analysis of the recurrent disengagement events data, • How to model the event process, and what kind of parametric forms should be used? • Does the parametric form provide an adequate fit to the data, and are there any other flexible forms for modeling? • Is there any population heterogeneity in the event processes from multiple test units? To answer those practical questions, we develop a statistical framework for modeling and analyzing the recurrent events data from AV driving tests. Specifically, we use the NHPP model to describe the disengagement event process with adjustment for the time-varying mileage data using traditional parametric models in software reliability for the intensity functions. We also propose a new nonparametric model based on 2 monotonic splines to describe the event process. The spline model is flexible enough to fit various patterns in the event process and can also be used to assess if the fully-parametric model provides an adequate fit. We develop inference procedures for selecting the best models and quantifying uncertainty using the fractional-random-weight bootstrap. The parametric models and spline models can be used as complementary tools. In addition, we use the gamma frailty model to quantify and assess heterogeneity in the event process. From the California driving study, we use data from four manufacturers that have been conducting extensive AV driving tests in California. We apply the developed methods to analyze the recurrent events data from the four AV manufacturers. Based on the modeling, we make inferences on the reliability of the AI systems in AV, and summarize interesting findings on the reliability of the AI systems in AV. Although our analysis focuses on the AI systems in AV, the statistical analysis can also be applied to assess the reliability of other AI systems. 1.2 Literature Review There is only a small amount of literature on reliability analysis of AI systems. Amodei et al. (2016) provided a general discussion on AI safety and outlined five concrete areas for AI safety research. Bosio et al. (2019) conducted a reliability analysis of deep convolutional neural network (CNN) developed for automotive applications using fault injections. Goldstein et al. (2020) investigated the impact of transient faults on the reliability of compressed deep CNN. Zhao et al. (2020) proposed a safety framework based on Bayesian inference for critical systems using deep learning models. Alshemali and Kalita (2020) provided a review on improving the reliability of natural language processing. Due to the limited availability of test data, statistical reliability analysis of AI reliability/safety is in an emerging stage. As an example of the modeling of the reliability and safety of AV, Kalra and Paddock (2016) used a statistical hypothesis testing approach to determine the needed miles of driving to demonstrate AV safety. Asljung,˚ Nilsson, and Fredriksson (2017) used extreme value theory to model the safety of AV. Michelmore et al. (2019) designed a statistical framework to evaluate the safety of deep neural network controllers and assessed the safety of AV. Burton et al. (2020) provided a multi-disciplinary perspective on the safety of AV from engineering, ethics, and law aspects. Most existing modeling framework, however, does not involve large scale field-testing data, which is essential for reliability assessment. The California driving test data provide unique opportunities for data analysis. Regarding the analysis of the California driving data, Dixit, Chand, and Nair (2016) and Favar`o,Eurich, and Nader (2018) analyzed the causes of disengagement events using the California driving test data up to 2017 and showed the relationship between disengagement events per miles 3 and cumulative miles. Lv et al. (2018) performed a descriptive analysis of the causes of disengagement events using the California driving test data from 2014 to 2015, and concluded that software issues and limitations were the most common reasons for disengagement events. Banerjee et al. (2018) used linear regressions to model the relationship between disengagement per mile and cumulative miles using the data from 2016 to 2017. Merkel (2018) conducted data analysis on the California driving data from 2015 to 2017 with aggregated counts data and least-squares fit. Zhao et al. (2019) proposed a general conservative Bayesian inference method to estimate the rate of events (crashes and fatality) and illustrated it with the California driving test data. Boggs, Wali, and Khattak (2020) did an exploratory analysis for AV crashes from the California driving study. So far, there is no comprehensive statistical treatment for the analysis of AI reliability and especially for AV reliability. Starting in 2018, the exact disengagement event time can be extracted from the California DMV report, which makes it possible to apply recurrent events modeling techniques. In the reliability literature, NHPP models are widely used to analyze recurrent events. Zuo, Meeker, and Wu (2008), and Hong, Li, and Osborn (2015) analyzed recurrent events data with window-observations, which has similar data types with the disengagement events data from the California driving study. Parametric models, such as the Musa-Okumoto model (e.g., Musa and Okumoto 1984) and the
Load more

Recommended publications
  • Paving the Way for Self-Driving Vehicles”
    June 13, 2017 The Honorable John Thune, Chairman The Honorable Bill Nelson, Ranking Member U.S. Senate Committee on Commerce, Science & Transportation 512 Dirksen Senate Office Building Washington, DC 20510 RE: Hearing on “Paving the Way for Self-Driving Vehicles” Dear Chairman Thune and Ranking Member Nelson: We write to your regarding the upcoming hearing “Paving the Way for Self-Driving Vehicles,”1 on the privacy and safety risks of connected and autonomous vehicles. For more than a decade, the Electronic Privacy Information Center (“EPIC”) has warned federal agencies and Congress about the growing risks to privacy resulting from the increasing collection and use of personal data concerning the operation of motor vehicles.2 EPIC was established in 1994 to focus public attention on emerging privacy and civil liberties issues. EPIC engages in a wide range of public policy and litigation activities. EPIC testified before the House of Representatives in 2015 on “the Internet of Cars.”3 Recently, EPIC 1 Paving the Way for Self-Driving Vehicles, 115th Cong. (2017), S. Comm. on Commerce, Science, and Transportation, https://www.commerce.senate.gov/public/index.cfm/pressreleases?ID=B7164253-4A43- 4B70-8A73-68BFFE9EAD1A (June 14, 2017). 2 See generally EPIC, “Automobile Event Data Recorders (Black Boxes) and Privacy,” https://epic.org/privacy/edrs/. See also EPIC, Comments, Docket No. NHTSA-2002-13546 (Feb. 28, 2003), available at https://epic.org/privacy/drivers/edr_comments.pdf (“There need to be clear guidelines for how the data can be accessed and processed by third parties following the use limitation and openness or transparency principles.”); EPIC, Comments on Federal Motor Vehicle Safety Standards; V2V Communications, Docket No.
    [Show full text]
  • Autonomous Vehicles on the Road from the Perspective of a Manufacturer's Liability for Damages
    Autonomous Vehicles on the Road from the Perspective of a Manufacturer's Liability for Damages IUC International Maritime and Transport Law Course International Maritime and Transport Law – Transport Law de Lege Ferenda Dubrovnik, 9 September 2020 Contents 1. Introduction - definitions, perspective 2. Challenges - current set of rules; AV-AV, AV-CV, AV-rest 3. Opportunities - vision for future 4. Summary Conclusion Is there a need for more regulation in order to help the production of AVs and mitigate damages? 1. AVs to be treated as conventional vehicles, i.e. as any other product, movable 2. Treat them as elevators/lifts or as autopilot technology 3. New legal framework Current legal framework • National regulations • EU strategies/investments • Independent bodies/entities and their recommendations • Good practices What is an AV? • a vehicle enabled with technology that has the capability of operating or driving the vehicle without the active control or monitoring of a natural person - Maurice Schellekens, Self-driving cars and the chilling effect of liability law • 3 elements: 1. Means (AI or similar technology) 2. Purpose of the means 3. Way of operating the means (active control or monitoring of a human person) • AV as any other movable Waymo’s self driving car, 2020 Source: https://www.google.com/search?q=Waymo&rlz=1C1GCEA_enHR912HR912&sxsrf=ALeKk00G8P_y2Ik0neIaDNxJlqcjKMQBlw:1599407756496&source=lnms&tbm=isch&sa=X&ved=2ahUKEwjR67SZ8tTrAhXSTcAKHZATCDQ Q_AUoAXoECBgQAw&biw=1366&bih=657#imgrc=z71dtWbxBXnwgM Tesla model 3, 2020 Source:
    [Show full text]
  • Model Based Systems Engineering Approach to Autonomous Driving
    DEGREE PROJECT IN ELECTRICAL ENGINEERING, SECOND CYCLE, 30 CREDITS STOCKHOLM, SWEDEN 2018 Model Based Systems Engineering Approach to Autonomous Driving Application of SysML for trajectory planning of autonomous vehicle SARANGI VEERMANI LEKAMANI KTH ROYAL INSTITUTE OF TECHNOLOGY SCHOOL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE Author Sarangi Veeramani Lekamani [email protected] School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Place for Project Sodertalje, Sweden AVL MTC AB Examiner Ingo Sander School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Supervisor George Ungureanu School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Industrial Supervisor Hakan Sahin AVL MTC AB Abstract Model Based Systems Engineering (MBSE) approach aims at implementing various processes of Systems Engineering (SE) through diagrams that provide different perspectives of the same underlying system. This approach provides a basis that helps develop a complex system in a systematic manner. Thus, this thesis aims at deriving a system model through this approach for the purpose of autonomous driving, specifically focusing on developing the subsystem responsible for generating a feasible trajectory for a miniature vehicle, called AutoCar, to enable it to move towards a goal. The report provides a background on MBSE and System Modeling Language (SysML) which is used for modelling the system. With this background, an MBSE framework for AutoCar is derived and the overall system design is explained. This report further explains the concepts involved in autonomous trajectory planning followed by an introduction to Robot Operating System (ROS) and its application for trajectory planning of the system. The report concludes with a detailed analysis on the benefits of using this approach for developing a system.
    [Show full text]
  • Waymo Rolls out Autonomous Vans Without Human Drivers 7 November 2017, by Tom Krisher
    Waymo rolls out autonomous vans without human drivers 7 November 2017, by Tom Krisher get drowsy, distracted or drunk. Google has long stated its intent to skip driver- assist systems and go directly to fully autonomous driving. The Waymo employee in the back seat won't be able to steer the minivan, but like all passengers, will be able to press a button to bring the van safely to a stop if necessary, Waymo said. Within a "few months," the fully autonomous vans will begin carrying volunteer passengers who are now taking part in a Phoenix-area test that includes use of backup drivers. Waymo CEO John Krafcik, who was to make the In this Sunday, Jan. 8, 2017, file photo, a Chrysler announcement Tuesday at a conference in Pacifica hybrid outfitted with Waymo's suite of sensors Portugal, said the company intends to expand the and radar is shown at the North American International testing to the entire 600-square-mile Phoenix area Auto Show in Detroit. Waymo is testing vehicles on and eventually bring the technology to more cities public roads with only an employee in the back seat. The around the world. It's confident that its system can testing started Oct. 19 with an automated Chrysler Pacifica minivan in the Phoenix suburb of Chandler, Ariz. handle all situations on public roads without human It's a major step toward vehicles driving themselves intervention, he said. without human backups on public roads. (AP Photo/Paul Sancya, File) "To have a vehicle on public roads without a person at the wheel, we've built some unique safety features into this minivan," Krafcik said in remarks prepared for the conference.
    [Show full text]
  • A Hierarchical Control System for Autonomous Driving Towards Urban Challenges
    applied sciences Article A Hierarchical Control System for Autonomous Driving towards Urban Challenges Nam Dinh Van , Muhammad Sualeh , Dohyeong Kim and Gon-Woo Kim *,† Intelligent Robotics Laboratory, Department of Control and Robot Engineering, Chungbuk National University, Cheongju-si 28644, Korea; [email protected] (N.D.V.); [email protected] (M.S.); [email protected] (D.K.) * Correspondence: [email protected] † Current Address: Chungdae-ro 1, Seowon-Gu, Cheongju, Chungbuk 28644, Korea. Received: 23 April 2020; Accepted: 18 May 2020; Published: 20 May 2020 Abstract: In recent years, the self-driving car technologies have been developed with many successful stories in both academia and industry. The challenge for autonomous vehicles is the requirement of operating accurately and robustly in the urban environment. This paper focuses on how to efficiently solve the hierarchical control system of a self-driving car into practice. This technique is composed of decision making, local path planning and control. An ego vehicle is navigated by global path planning with the aid of a High Definition map. Firstly, we propose the decision making for motion planning by applying a two-stage Finite State Machine to manipulate mission planning and control states. Furthermore, we implement a real-time hybrid A* algorithm with an occupancy grid map to find an efficient route for obstacle avoidance. Secondly, the local path planning is conducted to generate a safe and comfortable trajectory in unstructured scenarios. Herein, we solve an optimization problem with nonlinear constraints to optimize the sum of jerks for a smooth drive. In addition, controllers are designed by using the pure pursuit algorithm and the scheduled feedforward PI controller for lateral and longitudinal direction, respectively.
    [Show full text]
  • An Introduction of Autonomous Vehicles and a Brief Survey
    Journal of Critical Reviews ISSN- 2394-5125 Vol 7, Issue 13, 2020 AN INTRODUCTION OF AUTONOMOUS VEHICLES AND A BRIEF SURVEY 1Tirumalapudi Raviteja, 2Rajay Vedaraj I.S 1Research Scholar, School of Mechanical Engineering, Vellore instutite of technology, Tamilnadu, India, Email: [email protected] . 2Professor, School of Mechanical Engineering, Vellore instutite of technology, Tamilnadu, India, Email: [email protected] Received: 09.04.2020 Revised: 10.05.2020 Accepted: 06.06.2020 Abstract: An autonomous car is also called a self-driving car or driverless car or robotic car. Whatever the name but the aim of the technology is the same. Down the memory line, autonomous vehicle technology experiments started in 1920 only and controlled by radio technology. Later on, trails began in 1950. From the past few years, updating automation technology day by day and using all aspects of using in regular human life. The present scenario of human beings is addicted to automation and robotics technology using like agriculture, medical, transportation, automobile and manufacturing industries, IT sector, etc. For the last ten years, the automobile industry came forward to researching autonomous vehicle technology (Waymo Google, Uber, Tesla, Renault, Toyota, Audi, Volvo, Mercedes-Benz, General Motors, Nissan, Bosch, and Continental's autonomous vehicle, etc.). Level-3 Autonomous cars came out in 2020. Everyday autonomous vehicle technology researchers are solving challenges. In the future, without human help, robots will manufacture autonomous cars using IoT technology based on customer requirements and prefer these vehicles are very safe and comfortable in transportation systems like human traveling or cargo. Autonomous vehicles need data and updating continuously, so in this case, IoT and Artificial intelligence help to share the information device to the device.
    [Show full text]
  • AUTONOMOUS VEHICLES the EMERGING LANDSCAPE an Initial Perspective
    AUTONOMOUS VEHICLES THE EMERGING LANDSCAPE An Initial Perspective 1 Glossary Abbreviation Definition ACC Adaptive Cruise Control - Adjusts vehicle speed to maintain safe distance from vehicle ahead ADAS Advanced Driver Assistance System - Safety technologies such as lane departure warning AEB Autonomous Emergency Braking – Detects traffic situations and ensures optimal braking AUV Autonomous Underwater Vehicle – Submarine or underwater robot not requiring operator input AV Autonomous Vehicle - vehicle capable of sensing and navigating without human input CAAC Cooperative Adaptive Cruise Control – ACC with information sharing with other vehicles and infrastructure CAV Connected and Autonomous Vehicles – Grouping of both wirelessly connected and autonomous vehicles DARPA US Defense Advanced Research Projects Agency - Responsible for the development of emerging technologies EV Electric Vehicle – Vehicle that used one or more electric motors for propulsion GVA Gross Value Added - The value of goods / services produced in an area or industry of an economy HGV Heavy Goods Vehicle – EU term for any truck with a gross combination mass over 3,500kg (same as US LGV) HMI Human Machine Interface – User interface between a vehicle and the driver / passenger IATA International Air Transport Association - Trade association of the world’s airlines LIDAR Light Detection and Ranging - Laser-based 3D scanning and sensing MaaS Mobility as a Service - Mobility solutions that are consumed as a service rather than purchased as a product ODD Operational Design
    [Show full text]
  • Autonomous Vehicles “Pedal to the Metal Or Slamming on the Brakes?” Worldwide Regulation of Autonomous Vehicles Norton Rose Fulbright: Where Can We Take You Today?
    Financial institutions Energy Infrastructure, mining and commodities Transport Technology and innovation Life sciences and healthcare Autonomous vehicles “Pedal to the metal or slamming on the brakes?” Worldwide regulation of autonomous vehicles Norton Rose Fulbright: Where can we take you today? Paul Keller Huw Evans Partner, New York Partner, London Tel + 1 212 318 3212 Tel + 44 20 7444 2110 [email protected] [email protected] Frank Henkel Barbara Li Partner, Munich Partner, Beijing Tel + 49 89 212148 456 Tel + 86 10 6535 3130 [email protected] [email protected] More than 50 locations, including Houston, New York, London, Toronto, Hong Kong, Singapore, Sydney, Johannesburg and Dubai. Attorney advertising Autonomous vehicles “Pedal to the metal or slamming on the brakes?” Worldwide regulation of autonomous vehicles Norton Rose Fulbright – September 2018 03 Contents I. Introduction 05 II. Australia 06 III. Canada 30 IV. China 35 V. France 39 VI. Germany 43 VII. Hong Kong 57 VIII. India 62 IX. Indonesia 74 X. Japan 77 XI. Mexico 86 XII. Monaco 89 XIII. Netherlands 92 XIV.Nordic Region (Denmark, Finland, Norway and Sweden) 99 XV. Poland 102 XVI. Russia 106 XVII. Singapore 111 XVIII. South Africa 123 XIX. South Korea 127 XX. Thailand 132 XXI. Turkey 134 XXII. United Kingdom 137 XXIII. United States 149 04 Norton Rose Fulbright – September 2018 Autonomous vehicles – “Pedal to the metal or slamming on the brakes?” Worldwide regulation of autonomous vehicles I. Introduction Norton Rose Fulbright’s third annual Autonomous Vehicle White Paper, its most ambitious to date, addresses the worldwide regulatory landscape facing the autonomous vehicle market.
    [Show full text]
  • Supplementary Submission Intellectual Property And
    MAY 2017 HOUSE OF REPRESENTATIVES STANDING COMMITTEE ON INDUSTRY, INNOVATION, SCIENCE AND RESOURCES SUPPLEMENTARY SUBMISSION INTELLECTUAL PROPERTY AND SELF-DRIVING CARS: WAYMO VS UBER DR MATTHEW RIMMER PROFESSOR OF INTELLECTUAL PROPERTY AND INNOVATION LAW FACULTY OF LAW QUEENSLAND UNIVERSITY OF TECHNOLOGY Queensland University of Technology 2 George Street GPO Box 2434 Brisbane Queensland 4001 Australia Work Telephone Number: SUPPLEMENTARY SUBMISSION INTELLECTUAL PROPERTY AND SELF-DRIVING CARS: WAYMO VS UBER Matthew Rimmer While the Australian Parliament has been inquiring into social issues relating to land-based driverless vehicles in Australia since February 2017, intellectual property litigation has erupted in the courts between Waymo (Google’s Self-Driving Car Project) and Uber in the United States. The case has attracted much public attention. Alex Davies has reflected: Until today, the race to build a self-driving car seemed to hinge on who had the best technology. Now it’s become a case of full-blown corporate intrigue. Alphabet’s self-driving startup, Waymo, is suing Uber, accusing the ridesharing giant of stealing critical autonomous driving technology. If the suit goes to trial, Apple’s legal battle with Samsung could wind up looking tame by comparison.1 The intellectual property dispute could have significant implications for competition in respect of self-driving cars and autonomous vehicles. The New York Times has noted that ‘companies in Silicon Valley and Detroit are betting big on self-driving car technology’ and ‘the
    [Show full text]
  • Autonomous Vehicles Future: Driverless Cars
    Executive Insights Volume XIX, Issue 58 Mapping the Road to Autonomous Vehicles There’s no doubt that over the long term, 3. Industrial: Discovering and organizing the right business autonomous vehicles (better known as self-driving model to produce a commercially viable product cars), combined with electrification and shared While these challenges are significant, they will eventually be overcome. The path forward on No. 3 in particular (creating mobility, will have a massive impact on society. a business model to produce a sellable product) is just becoming clear. Many pundits debate the extent and speed of the expected effects. Will autonomy act as a “lighter fluid” for the spread of shared mobility services? How soon will urban real estate Figure 1 developers be freed from the need to provide space for parking? SAE International’s definitions of automation levels for on-road vehicles What will the impact on logistics do to retail? We like to say that these potential long-term effects depend on • Level 0: No automation (full driver control) how we get “from 1 to 100” — that is, from the launch of self- • Level 1: Driver assistance (vehicle controls either driving cars to a day when autonomous mobility is ubiquitous. steering or speed under certain conditions) But while prognostication is fun, the map to that destination is still far from clear. • Level 2: Partial automation (vehicle controls both steering and speed under certain conditions) What is becoming clearer, however, is the first leg of the journey, • Level 3: Conditional automation (total vehicle control or how we get “from 0 to 1” — from where we are today to the with expected human intervention) successful commercialization of the first fully self-driving vehicle.
    [Show full text]
  • The Study on Innovation, Development and Implementation
    ISSN (Online) 2581-9429 IJAR SCT ISSN (Print) 2581-XXXX International Journal of Advanced Research in Science, Communication and Technology (IJARSCT) Volume 11, Issue 1, November 2020 Impact Factor: 4.819 The Study on Innovation, Development and Implementation of the Self-driving Car Aniruddha Chaki Student, Department of Electrical Engineering Siliguri Institute of Technology, Siliguri, India Abstract: The development of the self-driving car is one of the greatest inventions of the century. With the technological advancement, the implementation of the autonomous vehicle has become the major attention among the researchers. This paper discusses the brief history of self-driving cars, its research and development, key technologies behind the self-driving, main aspects of implementing self-driving cars. The paper also describes some challenges with possible solutions to the fully autonomous vehicle in mass implementation. Keywords: Advanced Driver Assistance System (ADAS), autonomous, navigation, positioning, self- driving technology, radar, lidar, path planning, obstacle avoidance, Full Self driving (FSD), accidents, protests, advantages, challenges. I. INTRODUCTION In this 21st-century progress in technology has made man as omnipotent, omniscient and omnipresent as a god. It is being tried to find out and accomplish any work with higher efficiency, lesser cost, and least possible effort. This makes researchers explore the domain of Automation, Machine learning, and Artificial Intelligence to handle the hardest of the jobs which were once tedious and cumbersome for humans [1]. We are driving towards the future where humans will only be involved in high mental ability skills and all the other works will be automated [2]. In this paper, the previous researches in the field of self-driving have been studied.
    [Show full text]
  • The Impact of Automated Transport on the Role, Operations and Costs of Road Operators and Authorities in Finland
    The impact of automated transport on the role, operations and costs of road operators and authorities in Finland EU-EIP Activity 4.2 Facilitating automated driving Risto Kulmala, Juhani Jääskeläinen, Seppo Pakarinen Traficomin tutkimuksia ja selvityksiä Traficoms forskningsrapporter och utredningar Traficom Research Reports 6/2019 Traficom Research Reports 6/2019 Julkaisun päivämäärä 12.3.2019 Julkaisun nimi The impact of automated transport on the role, operations and costs of road operators and authorities in Finland (Automaattiajoneuvojen vaikutukset tienpitäjien ja viranomaisten rooliin, toimintaan ja kustannuksiin Suomessa) Tekijät Risto Kulmala, Juhani Jääskeläinen, Seppo Pakarinen Toimeksiantaja ja asettamispäivämäärä Liikennevirasto ja Trafi 22.3.2018 Julkaisusarjan nimi ja numero ISSN verkkojulkaisu) 2342-0294 Traficomin tutkimuksia ja selvityksiä ISBN (verkkojulkaisu) 978-952-311-306-0 6/2019 Asiasanat Automaattiajaminen, tieliikenne, automaattiauto, vaikutus, tienpitäjä. viranomainen, rooli, kustannukset, toiminta, Suomi Tiivistelmä Tämä kansallinen tutkimus tehtiin osana työpakettia ”Facilitating automated driving” EU:n CEF- ohjelman hankkeessa EU EIP keskittyen viiteen korkean tason automaattiajamisen sovellukseen: moottoritieautopilotti, automaattikuorma-autot niille osoitetuilla väylillä, automaattibussit sekaliikenteessä, robottitaksit sekä automaattiset kunnossapito- ja tietyöajoneuvot. Raportti kuvaa automaattiajamiseen liittyvät säädöspuitteet ja viranomaisstrategiat eri puolilla maailmaa ja etenkin Euroopassa. Tutkimus
    [Show full text]